Let a Dot assemble a narrated video edit

A creator used a Dot to find footage, lay in visuals, and add captions around a recorded narration in Descript.

Done with Dots· Intermediate

What they did
Matt Paige fed his Dot two Instagram clips as style guides plus a Higgsfield characters video. His Descript project already included his spoken track and a launch-film overlay, so the Dot could work from that base. It pulled official demo clips, built the opening split, added B-roll, insets, progressive captions, logos, and removed extra footage across several review rounds.
How it went
The finished piece was a short-form video. The Dot cut about two and a half minutes of extra material and carried Matt’s manual edits into matching sections, while the voice track and creative calls stayed with him.
Tips
Give the agent specific visual references and spell out details like font, size, and placement. Plan on a few export-and-review cycles, and check the small stuff yourself before you approve anything final.

Try it yourself with Dots

I have a narrated video at [path or link to narration/script] and a rough project in [editor name] at [project link]. Use [reference clips or links] to match the visual style. Find suitable footage for each section, assemble a first-pass edit over my narration, add captions, and place logos or inset clips where they fit. After each draft, show me what you changed and wait for my approval before you export, publish, send, or delete anything. If I ask for revisions, apply them only to the sections I point out and then stop for another review.

Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.

Read the original on mattpaige68.substack.com ↗

Get 3 agent uses like this every morning

With the day's top AI news. Free, and one click to unsubscribe.